Free Shipping Is Not Free: A Data-Driven Model to Design Free-Shipping Threshold Policies.

Abstract

Online retailers often offer free shipping threshold policies: customers who purchase more than a threshold amount are not charged an additional fee for shipping. This paper provides a data-driven analytical model to (i) assess the profitability of a retailer’s current shipping threshold policy and (ii) identify the best freeshipping threshold policy for a retailer. The model is estimated from actual transaction and product return data. The model explicitly accounts for changes in customer shopping behavior due to a free shipping threshold, including strategically adding items to a shopping basket to receive free shipping, which we call orderpadding, and the subsequent adjustment in product return decisions. Roughly speaking, according to our model, a retailer that offers a free shipping threshold policy should set the threshold slightly abovethe average shopping basket amount. We calibrate our model to data from an online apparel retailer and determine that its decision to offer a lower free shipping threshold reduced its profitability considerably.This result is robust to a number of assumptions regarding the impact on long-run sales and possible price adjustments. We conclude that free shipping threshold policies are profitable only under a limited set of restrictive conditions.